Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
Python agent-loopagent-pluginsagent-skillsagenticai-agentsclaude-codeclosed-loopcursorgarry-tangbraingstackknowledge-managementloop-engineeringobsidianpeople-crmproductivitysecond-brainself-evolvingverification-harnessworker-agents
{
"name": "cog-second-brain",
"version": "3.16.0",
"description": "Self-evolving second brain with 43 AI agent skills, 10 agents, and people CRM. Closed-loop harness release: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with a north-star acceptance gate, plus craft skills for writing, visual work, and a paired anti-slop design system for marketing and product UI. Inspired by Garry Tan's gstack specialist sessions, gbrain knowledge patterns, and dwarves-kit closed-loop execution. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, and any markdown-reading agent.",
"author": {
"name": "Huy Tieu",
"url": "https://github.com/huytieu"
},
"homepage": "https://github.com/huytieu/COG-second-brain",
"repository": {
"type": "git",
"url": "https://github.com/huytieu/COG-second-brain"
},
"license": "MIT",
"keywords": [
"second-brain",
"knowledge-management",
"obsidian",
"ai-agents",
"productivity",
"garry-tan",
"gstack",
"gbrain",
"worker-agents",
"people-crm",
"braindump",
"daily-brief",
"team-intelligence",
"claude-code",
"antigravity",
"cursor",
"kiro",
"gemini-cli",
"codex",
"agentic",
"self-evolving",
"personal-intelligence",
"note-taking",
"specialist-sessions",
"loop-engineering",
"agent-loop",
"memory-hygiene",
"runtime-trust",
"content-factory",
"verification",
"skill-distillation",
"v-model",
"closed-loop",
"verification-harness",
"evidence-ledger",
"ultragoal",
"risk-lanes",
"verifier-agents",
"retrospective",
"no-ai-slop",
"data-viz",
"design-systems",
"ui-ux",
"anti-slop",
"product-design"
],
"category": "productivity",
"tags": [
"knowledge-management",
"obsidian",
"second-brain",
"ai-agents",
"productivity",
"garry-tan",
"gstack",
"gbrain",
"worker-agents",
"people-crm",
"claude-code",
"cursor",
"specialist-sessions"
],
"skills": [
{
"name": "onboarding",
"path": ".claude/skills/onboarding/SKILL.md",
"description": "Personalize COG for your workflow - creates profile, interests, and watchlist files (run this first!)"
},
{
"name": "braindump",
"path": ".claude/skills/braindump/SKILL.md",
"description": "Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction"
},
{
"name": "daily-brief",
"path": ".claude/skills/daily-brief/SKILL.md",
"description": "Generate personalized news intelligence with verified sources (7-day freshness requirement)"
},
{
"name": "weekly-checkin",
"path": ".claude/skills/weekly-checkin/SKILL.md",
"description": "Cross-domain pattern analysis and strategic reflection for weekly review"
},
{
"name": "knowledge-consolidation",
"path": ".claude/skills/knowledge-consolidation/SKILL.md",
"description": "Build frameworks from scattered insights across all braindumps and notes"
},
{
"name": "url-dump",
"path": ".claude/skills/url-dump/SKILL.md",
"description": "Quick capture URLs with automatic content extraction, insights, and categorization into knowledge booklets"
},
{
"name": "loop-engineering",
"path": ".claude/skills/loop-engineering/SKILL.md",
"description": "Shared loop-engineering reference for iterative skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns"
},
{
"name": "team-brief",
"path": ".claude/skills/team-brief/SKILL.md",
"description": "Cross-reference GitHub, Linear, Slack, PostHog, meetings, and braindumps into a daily team intelligence brief with Linear sync-back"
},
{
"name": "meeting-transcript",
"path": ".claude/skills/meeting-transcript/SKILL.md",
"description": "Process meeting recordings into structured decisions, action items, and team dynamics"
},
{
"name": "comprehensive-analysis",
"path": ".claude/skills/comprehensive-analysis/SKILL.md",
"description": "Deep 7-day analysis for weekly reviews, board prep, or strategic planning"
},
{
"name": "scout",
"path": ".claude/skills/scout/SKILL.md",
"description": "Triage a URL or tool (verify, classify, and check fit) before deciding whether to save it"
},
{
"name": "update-cog",
"path": ".claude/skills/update-cog/SKILL.md",
"description": "Check for and apply upstream COG framework updates without touching personal content"
},
{
"name": "memory-hygiene",
"path": ".claude/skills/memory-hygiene/SKILL.md",
"description": "Periodic trust sweep of persistent memory - re-verify environment-dependent claims, stamp last_verified + confidence, propose archiving drifted entries"
},
{
"name": "content-factory",
"path": ".claude/skills/content-factory/SKILL.md",
"description": "Autonomous content pipeline - scout announcements, triage by trend momentum and personal angle, produce and publish with ledger dedup, volume caps, and post-condition verification"
},
{
"name": "auto-research",
"path": ".claude/skills/auto-research/SKILL.md",
"description": "Deep strategic research engine with parallel research threads and actionable analysis"
},
{
"name": "create-user-story",
"path": ".claude/skills/create-user-story/SKILL.md",
"description": "Create user stories with duplicate checking across Linear, GitHub Issues, or Jira"
},
{
"name": "generate-prd",
"path": ".claude/skills/generate-prd/SKILL.md",
"description": "Draft PRDs with approval gate before publishing to Confluence or Notion"
},
{
"name": "generate-release-notes",
"path": ".claude/skills/generate-release-notes/SKILL.md",
"description": "Generate release notes from GitHub milestones, Linear cycles, or manual input"
},
{
"name": "export-open-issues",
"path": ".claude/skills/export-open-issues/SKILL.md",
"description": "Audit and export open issues from any project tracker"
},
{
"name": "publish-to-confluence",
"path": ".claude/skills/publish-to-confluence/SKILL.md",
"description": "Publish vault markdown files to Confluence"
},
{
"name": "update-knowledge-base",
"path": ".claude/skills/update-knowledge-base/SKILL.md",
"description": "Maintain product knowledge base from releases and feature updates"
},
{
"name": "closed-loop",
"path": ".claude/skills/closed-loop/SKILL.md",
"description": "V-model execute pipeline - plan, build, component verify, integration verify, acceptance; the worker never grades its own homework and every evidence row traces to an AC-n criterion"
},
{
"name": "ultragoal",
"path": ".claude/skills/ultragoal/SKILL.md",
"description": "Run a goal too big for one session as a chain of phases, each its own full closed-loop run, with cross-session state and a final north-star acceptance gate"
},
{
"name": "harvest",
"path": ".claude/skills/harvest/SKILL.md",
"description": "Capture durable session learnings, stage them for human promotion into knowledge, and propose skill/CLAUDE.md patches - never writes durable knowledge unapproved"
},
{
"name": "retro",
"path": ".claude/skills/retro/SKILL.md",
"description": "CP-7 retrospective - audit checkpoints, evidence quality, and action items; closes the V-model cycle and feeds the next run"
},
{
"name": "review-cockpit",
"path": ".claude/skills/review-cockpit/SKILL.md",
"description": "One living review document per multi-item session - cockpit header plus per-item cards you approve or request changes on directly in the doc"
},
{
"name": "no-ai-slop",
"path": ".claude/skills/no-ai-slop/SKILL.md",
"description": "Edit drafts into sharper, more human writing while preserving personal voice, or detect AI-slop patterns without rewriting"
},
{
"name": "editorial-illustrations",
"path": ".claude/skills/editorial-illustrations/SKILL.md",
"description": "Generative guide for meaning-carrying editorial data-illustrations - teaches the claim-to-geometry method, renders self-contained theme-aware HTML/SVG figures"
},
{
"name": "data-forms",
"path": ".claude/skills/data-forms/SKILL.md",
"description": "Pick the right form for a dataset so the finding lands in three seconds - 20+ chart and diagram forms with when-to-use, failure modes, and encoding discipline"
},
{
"name": "museum-art",
"path": ".claude/skills/museum-art/SKILL.md",
"description": "Source authentic high-res public-domain artwork from museum open-access APIs instead of AI-generated or generic-stock imagery"
},
{
"name": "daily-journal",
"path": ".claude/skills/daily-journal/SKILL.md",
"description": "A passive daily work journal the agent keeps for you - appends entries after meaningful work, runs a guided reflection on request"
},
{
"name": "taste-skill",
"path": ".claude/skills/taste-skill/SKILL.md",
"description": "Anti-slop frontend skill for landing pages, portfolios, and redesigns - reads the brief, states a design read, and ships interfaces that do not look templated"
},
{
"name": "product-ui-taste",
"path": ".claude/skills/product-ui-taste/SKILL.md",
"description": "Anti-slop skill for dense product surfaces (dashboards, tables, forms, wizards, admin consoles) - frame-first, correct at every edge case real data produces"
},
{
"name": "slop-gate",
"description": "Refuse AI-slop tells in anything about to be written, published, or sent; runs in CI or as a hook",
"path": ".claude/skills/slop-gate/SKILL.md"
},
{
"name": "voice-baseline",
"description": "Measure the words and sentence shapes you over-use so an agent stops amplifying your tics",
"path": ".claude/skills/voice-baseline/SKILL.md"
},
{
"name": "release-video",
"path": ".claude/skills/release-video/SKILL.md",
"description": "Turn a product release into a motion recap video and explained per-feature demos: deterministic HTML scenes, sound effects tied to motion, music composed to the timeline"
},
{
"name": "blog-publish",
"path": ".claude/skills/blog-publish/SKILL.md",
"description": "Write and publish a post to your own static blog: TL;DR, ASCII art, markdown twin for agents, deploy, and social distribution"
},
{
"name": "feature-doc",
"path": ".claude/skills/feature-doc/SKILL.md",
"description": "Document a shipped feature from the live app: real screenshots and a screen recording, a docs article with how-to and use cases, verified before publish"
},
{
"name": "release-comms",
"path": ".claude/skills/release-comms/SKILL.md",
"description": "Turn a deployment runsheet and a GitHub milestone into a customer release note with real media, docs updates, and a Slack announcement draft"
},
{
"name": "social-media-kit",
"path": ".claude/skills/social-media-kit/SKILL.md",
"description": "Attach native media (teaser video, GIF, card images) to every social post, with per-platform upload steps"
},
{
"name": "terminal-replica",
"path": ".claude/skills/terminal-replica/SKILL.md",
"description": "Reproduce your real terminal and CLI agents (Claude Code, Codex, Gemini CLI) faithfully in graphics and video frames"
},
{
"name": "vector-cover",
"path": ".claude/skills/vector-cover/SKILL.md",
"description": "Flat vector editorial cover illustrations in HTML and SVG, rendered to a 2400x960 PNG with headless Chrome"
},
{
"name": "youtube-video-kit",
"path": ".claude/skills/youtube-video-kit/SKILL.md",
"description": "YouTube packaging: thumbnail, animated opening title, ElevenLabs music bed, and the upload metadata bundle"
}
],
"metadata": {
"pluginRoot": ".",
"architecture": "multi-agent-skill-pack",
"features": [
"Self-evolving intelligence with pattern recognition",
"Self-healing system with auto-updating cross-references",
"Verification-first approach (no AI hallucinations)",
"Privacy-first architecture with strict domain separation",
"Plain text markdown files (no database, no vendor lock-in)",
"Multi-device sync via iCloud (iPhone, iPad, Mac)",
"Git version control for tracking thinking evolution",
"Agent-surface validator for manifest/docs consistency",
"Worker agent architecture with model routing (Sonnet workers, Opus lead)",
"People CRM with tiered enrichment and evidence-based profiles",
"Runtime trust: memory-hygiene sweeps with last_verified + confidence stamps",
"Skill post-condition checks - observe the mutated artifact before reporting success",
"Skill distillation pattern: explore once with a strong model, execute cheap with a small one",
"V-model closed loop: decompose to falsifiable criteria, verify with evidence traced back to each one",
"Read-only verifier agents (task-verifier, integration-verifier) that observe artifacts, not worker summaries",
"Risk lanes: ceremony scales with blast radius instead of applying uniformly",
"Ultragoals: multi-session goals with per-phase verification and a final north-star acceptance gate",
"Cross-model flagship gate - a different model family catches a different error class",
"Paired anti-slop design skills: taste-skill owns marketing surfaces, product-ui-taste owns dense product UI"
],
"requirements": {
"obsidian": "Recommended for markdown file management",
"git": "Optional but recommended for version control and safe updates",
"claudeCode": "Recommended for the full 33-skill native experience",
"kiro": "Optional - ships 7 native core powers",
"geminiCli": "Optional - ships 7 native core commands",
"agentsMd": "Universal fallback surface for Codex and other markdown-reading agents"
},
"installation": {
"quickStart": "Clone the repo, cd into COG-second-brain, then run onboarding in your agent of choice",
"setupTime": "2-5 minutes",
"onboardingTime": "2 minutes",
"validation": "Run ./scripts/validate-agent-surface.sh before publishing or after framework updates"
},
"directoryStructure": {
".claude/skills": "33 Claude Code skills (full surface)",
".claude/agents": "10 agent definitions - 6 workers plus 4 read-only verifiers",
".claude/roles": "7 role packs for personalized skill and integration recommendations",
".kiro/powers": "7 Kiro powers (core workflows)",
".gemini/commands": "7 Gemini CLI commands (core workflows)",
".gemini/skills": "Detailed Gemini command playbooks",
"AGENTS.md": "Universal command surface for Codex and other agents",
"00-inbox": "Temporary processing area with profile and interests files",
"01-daily": "Daily briefs and check-ins",
"02-personal": "Personal domain (strict privacy)",
"03-professional": "Professional domain with competitive watchlist",
"04-projects": "Project-specific tracking",
"05-knowledge": "Consolidated insights and patterns",
".claude/lib": "Harness shell helpers (checkpoint recorder, risk-lane classifier)",
"WORKFLOW.md": "The V-model lifecycle: checkpoints, gate classes, evidence contract"
},
"skillArchitecture": {
"type": "agent-skills",
"skills": 33,
"workerAgents": 10,
"rolePacks": 7,
"invocation": "model-invoked",
"progressiveDisclosure": true,
"nativeSurfaces": {
"claudeCode": 33,
"antigravity": 33,
"kiro": 7,
"geminiCli": 7,
"agentsMd": 33
},
"description": "Self-contained skills with worker delegation and a read-only verification layer, full Claude Code and Antigravity surfaces, core native Kiro/Gemini surfaces, and AGENTS.md as the universal fallback"
}
}
}